Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1946 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5466. Min Act: -0.0000

Data Index: 784195 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4979. Min Act: -0.0000

Data Index: 799609 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5867. Min Act: -0.0001

Data Index: 799682 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4875. Min Act: -0.0000

Data Index: 38857 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4691. Min Act: -0.0000

Data Index: 676060 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4176. Min Act: -0.0000

Data Index: 667592 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3544. Min Act: -0.0001

Data Index: 577640 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4001. Min Act: -0.0001

Data Index: 1060024 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4174. Min Act: -0.0000

Data Index: 96093 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3974. Min Act: -0.0000

Data Index: 346359 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3801. Min Act: -0.0000

Data Index: 234808 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3500. Min Act: -0.0001

Data Index: 272468 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3380. Min Act: -0.0001

Data Index: 1015363 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3713. Min Act: -0.0001

Data Index: 888165 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3811. Min Act: -0.0001

Data Index: 1154926 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1206326 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3302. Min Act: -0.0000

Data Index: 1020547 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3428. Min Act: -0.0000

Data Index: 915089 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3556. Min Act: -0.0001

Data Index: 479015 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1318507 (C4 (Web Text))

Max Activating Token Index: 261